Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    all followed by descriptive verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    או
    0.45
     or
    0.45
     hoặc
    0.44
     或
    0.43
    )，
    0.43
    ו
    0.43
     arcs
    0.42
     অথবা
    0.41
     jede
    0.41
     manuals
    0.40
    POSITIVE LOGITS
     in
    0.41
    ay
    0.40
    ong
    0.38
    istä
    0.37
     of
    0.36
    ickey
    0.34
    在
    0.34
     hugely
    0.34
    ati
    0.33
     जगह
    0.33
    Act Density 0.026%

    No Known Activations